Hydroisomerisation and Hydrocracking of n-Heptane: Modelling and Optimisation Using a Hybrid Artificial Neural Network–Genetic Algorithm (ANN–GA)

Round 1

Reviewer 1 Report

Authors are requested to undertake the suggested comments.

Comments for author File: Comments.pdf

English is good, only minor corrections are required.

Author Response

Dear reviewer,

Thank you very much for effort on reviewing our paper. Fortunately, I have corrected the manuscript according to your useful comments. All the items which you mentioned are covered.

All the corrected items which you referred can be seen as red color text in the manuscript to facilitate the recheck process. Finally, we highly appreciate your notes which participate in upgrading our manuscript.

Author Response File: Author Response.pdf

Reviewer 2 Report

The manuscript is devoted to the development of a neural network for modeling the processes of hydrocracking and hydroisomerization of n-heptane. Usually the optimization of chemical processes is a complex routine task involving a large number of experiments. In my opinion, a successful system with the possibility of high control over the experiment and results was chosen for training the neural network.

The study was carried out at a high level and corresponds to the topic.

Is it possible to complicate the system to use a wider number of factors influencing the process? Is it possible to supplement the system with additional kinetic equations, as well as the cost of production? Can a neural network calculate the technological regime for the economic efficiency of the process?

Is it possible to expand the scope for processes with multi-component systems, such as catalytic cracking and others?

What are the authors' further plans to expand the scope?

Author Response

Dear reviewer,

Thank you very much for effort on reviewing our paper. Fortunately, I have corrected the manuscript according to your useful comments. All the items which you mentioned are covered.

All the corrected items which you referred can be seen as blue color text in the manuscript to facilitate the recheck process. Finally, we highly appreciate your notes which participate in upgrading our manuscript.

Author Response File: Author Response.pdf

Reviewer 3 Report

In the paper of “Hydroisomerisation and Hydrocracking of n-Heptane: Model-ling and Optimization Using a Hybrid Artificial Neural Net-work-Genetic Algorithm (ANN-GA)”, the authors used HY/HZSM-5 as the catalyst to catalyze cracking of n-heptane, and introduced ANN-GA to establish machine learning algorism which can predict the reaction results. There are some questions listed in the following.

1. The software information and detailed machine learning processes should be described in the main text.

2. ANN algorism needs a lot of experiment data to obtain a credible result, while in this paper, the data are seriously insufficient. It is recommended that at least 150-experiment data points should be used. This means, the authors can increase the numbers of variables, such as the ratio of HY to HZSM-5, reaction temperature (325^oC, 375^oC), etc.

Author Response

Dear reviewer,

Thank you very much for effort on reviewing our paper. Fortunately, I have corrected the manuscript according to your useful comments. All the items which you mentioned are covered.

All the corrected items which you referred can be seen as green color text in the manuscript to facilitate the recheck process. Finally, we highly appreciate your notes which participate in upgrading our manuscript.

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

The authors explained the results carefully, but I still can not agree with them. In this paper, the data points are really not enough for machine learning.

Some errors still existed.  Such as, "Table 3 The pparameters", should be "Table 3 The parameters".

Author Response

Dear reviewer, Thank you very much for effort on reviewing our paper. Please find the attach file.

Author Response File: Author Response.pdf